belay
01Plugin Claude Code
Plugin marketplace listing 10 plugins: acl-hook, no-shirk-hook, fs-acl-hook, branch-guard-hook, delegation-hook.
Plugin Claude Code
Plugin marketplace listing 10 plugins: acl-hook, no-shirk-hook, fs-acl-hook, branch-guard-hook, delegation-hook.
Skill Claude CodeCodex
Scaffold a new plugin in this belay marketplace. Use when the user asks to add/create/scaffold a new plugin, hook, skill, or command under plugins/. Creates plugins/ / with the standard layout, fills version 0.1.0, registers it in .claude-plugin/marketplace.json, and adds a row to the README plugin table.
Instructions file
Claude Code instructions for galilei2050/belay, covering claude.md — belay, what this repo is, before any commit: run make ci, bump plugin version on functional changes and adding a new plugin.
Plugin Claude Code
PreToolUse Bash gate enforcing a project ACL with pattern-based allow/ask/deny rules.
Hook
Runs before the agent uses a tool for Bash tool calls, executing acl_hook.py via python3. From galilei2050/belay.
Plugin Claude Code
PreToolUse file-tool gate: denies file edits (Write/Edit/MultiEdit/NotebookEdit) while a protected branch (main/master) is checked out.
Plugin Claude Code
Skill + three subagents that answer a "why is X like this?" question by enumerating every hypothesis first, then falsifying branches with evidence until one mechanism accounts for the whole effect.
Agent
Retrieves one narrow slice of fact for exactly one investigation hypothesis from sources reachable from this machine — code, files, logs, git history, databases, internal services and CLIs. Returns the exact command and its raw output, never an interpretation. Use when an investigation needs a fact fetched; not for…
Agent
Adversary for a single investigation hypothesis that already has supporting evidence — verified or partial. Attacks it seven ways (alternative cause for the same evidence, direction and timing, effect size, circularity, counter-case, selection bias, overlap with other verified leaves), gathering its own evidence…
Agent
Establishes facts that live outside this system for exactly one investigation hypothesis — known mechanisms, published benchmarks, vendor and provider incidents, status-page history, policy or platform changes, upstream release notes. Every fact returns with a source URL and a publication date, and "not found, here is…
Skill Claude CodeCodex
Explains a measured effect whose cause is genuinely unknown — a metric that moved, an incident nobody can account for, two sources reporting different numbers for the same thing, a regression that survived the obvious fix. Enumerates every candidate cause as a hypothesis tree before checking any of them, then kills…
Plugin Claude Code
PreToolUse delegation gate: subagents run in the background so the session is never frozen waiting for one, and each gets a 30 tool-call / 7-minute budget before its tools are cut off.
Plugin Claude Code
PreToolUse file-tool gate: a path-based ACL for Write/Edit/Read (the file-tool sibling of acl-hook).
Plugin Claude Code
Stop hook that blocks the agent from ending a turn with an ask-instead-of-do question.
Plugin Claude Code
A skill that writes PR descriptions a reviewer can act on, a CI script that takes a branch from a verdict through the merge and the deploy that follows it while printing only the failing log, and a PostToolUse hook that carries every commit through to a pushed branch, an open PR, a green CI and a change that is…
Command
Take the current branch's CI to a verdict, then the PR to merged, deployed and measured.
Command
Open or refresh the PR for the current branch, with a description a reviewer can act on.
Skill Claude CodeCodex
Writes or refreshes the description of a pull request — the body a reviewer reads before the diff. Use when opening a PR (gh pr create), when a push has made an existing PR's body stale, or when the user asks to write up / re-write / оформить a PR. Produces the failure with its measured numbers, a mermaid diagram of…
Plugin Claude Code
A panel of eight read-only reviewer subagents, dispatched by a PreToolUse hook over every commit of 64+ changed lines.
Agent
Reviews a commit for code that is bigger than the problem — long methods, deep nesting, speculative abstraction, unused parameters, dead code. Use when reviewing a diff for bloat, complexity, or over-engineering.
Agent
Reviews a commit's comments, docstrings, and prose documentation — checks each one describes the entity it is attached to (not something beside it), says why rather than what, is actually true, and links to the source instead of copying it. Use when reviewing a diff for comment or documentation quality.
Agent
Reviews a commit for whether the code actually computes the right answer — algorithm and business-logic errors, inverted conditions, off-by-one and boundary mistakes, unhandled edge cases, wrong ordering, concurrency and state errors. Use when reviewing a diff for functional correctness.
Agent
Reviews a commit for DRY violations — code that builds a second tower beside an existing one instead of modifying it. Use when reviewing a diff for duplication, copy-paste, parallel implementations, or reinvented utilities.
Agent
Reviews a commit for misplaced error handling and implicit contracts — guards against impossible states, swallowed exceptions and silent fallbacks, escape-hatch types, bare domain literals with no enum behind them, naive datetimes and dates compared as text, code that guesses at the shape of its input, and failure…